Configure, Deploy and Operate Nvidia Triton Inference Server - Rafay Product Documentation

Part 1: Setup

What Will You Do

This is Part 1 of a multi-part, self-paced quick start exercise. In this part, you will perform a few "one-time" tasks required for cluster provisioning.

Step 1: Cloud Credentials

Cloud credentials provide privileges to programmatically interact with your Amazon AWS account so that the lifecycle of infrastructure associated with the Amazon EKS cluster can be managed.

Step 2: Download RCTL

The RCTL CLI allows you to programmatically interact with the controller enabling users to construct sophisticated automation workflows.

Step 3: Clone Git Repository

Declarative specs for the Amazon EKS cluster and other resources are available in a Git repository

git clone https://github.com/RafaySystems/getstarted.git

Recap

At this point, you have everything setup and configured to provision the GPU enabled Amazon EKS Cluster that will run the Triton inference server.